Pedestrian Behavior Research Articles

Construction and Study of an Improved PP-Human Multi-Objective Tracking Method

Multiple objective tracking represents a crucial research focus within the realm of computer vision. It has a very broad application prospect in video surveillance, intelligent transportation, robot navigation and positioning and other fields.However, multi-target visual perception is affected by light, weather, occlusion and other factors, and is vulnerable to noise interference, faced with problems such as unstable image enhancement effect, target correlation accuracy and robustness.In this study, the PP-Human framework is applied to multi-target tracking. Through training and refinement of the PP-Human model, integration of a high-accuracy detector, enhancement of pedestrian re-identification (ReID) techniques, and optimization of the data association approach, the model's multi-object detection performance is enhanced, achieving efficient and precise multi-target tracking. Using the extended Market 150 dataset to comprehensively evaluate the performance of the proposed multi-objective tracking method, this paper improves the accuracy of multi-objective tracking by 5.0% and reaches 95.0% of MOTA through a series of optimization measures.To validate the efficacy and robustness of this approach, experimental evaluations were conducted. The refined PP-Human framework demonstrated strong performance in multi-target tracking tasks, establishing a reliable basis for practical applications such as pedestrian analysis, behavior recognition, and flow statistics.

Analysis of pedestrian crossing violations at an overpass location by using a logit model

Jaywalking significantly increases accident risks compared to marked crosswalks. Overpasses are often installed to address this, but violations continue. This study examines pedestrian behavior at overpass locations, focusing on 438 individuals recorded on video. Factors like parked vehicles, gender, age, group size, mobile phone distraction, carrying items, the number of waiting pedestrians upon arrival, waiting times, and traffic volume were analyzed. Since jaywalking is more frequent during off-peak hours when traffic is not congested, observations were made at random intervals during these times. A binary logit model was used to identify the factors influencing jaywalking. The study found that points of interest near overpasses significantly affect pedestrian behavior. Additionally, parked vehicles near the overpass reduce crossing distance, encouraging jaywalking. Policy recommendations include implementing parking restrictions and strategically locating overpasses to align with pedestrian movement patterns and nearby points of interest.

Human-UAV interactive perception: Skeleton-based iterative perspective optimization algorithm for UAV patrol tracking of large-scale pedestrian abnormal behavior

Human-UAV interactive perception: Skeleton-based iterative perspective optimization algorithm for UAV patrol tracking of large-scale pedestrian abnormal behavior

An evacuation model considering pedestrian group behavior under violent attacks

In recent years, violent attacks have garnered significant attention from the international community and gradually evolved into a global issue. In responding to such emergencies, effective emergency evacuation is an essential means to ensure public safety. In order to explore the pedestrian evacuation dynamics in violent attacks and understand the behavioral characteristics of individuals and the dynamic interactions of groups during the evacuation process, this paper proposes an agent-based cellular automata evacuation model. First, each agent is assigned several internal attributes such as life value, panic value, and movement speed, and the assignments fully take into account the heterogeneity of individuals. Next, by setting the attack strategy of attackers and the evacuation mechanism of pedestrians, the complex system is modeled from a microscopic perspective. Finally, the effects of critical factors on the pedestrian evacuation process, such as panic coefficient, crowd structure, group ratio, attack distance and intensity, attacker location and number, and counterattack probability, are discussed through simulation. The results show that the tension caused by moderate panic is beneficial, but excessive panic will lead to increased evacuation time and fatalities. Meanwhile, the group behavior among pedestrians causes them to move relatively lagging, and the evacuation efficiency decreases as the group scale increases. Additionally, increases in attack intensity, attack distance, and attacker number all result in more casualties, and the consequences are most severe when multiple attackers operate separately, but counterattacks by pedestrians can significantly improve the overall safety of evacuation. Our study can provide some reference and basis for emergency management under violent attacks.

Effects of risk information on pedestrian evacuation during fire emergencies: Virtual experiments and survey

In fire emergencies, pedestrians often face uncertainty about the safety of evacuation routes due to a lack of risk information, which makes the emergency evacuation highly challenging. Although risk information is crucial for effective evacuation, the effect of varying levels of risk information on fire evacuation remains insufficiently explored. This study aims to address this gap by investigating the influence of different levels of risk information on pedestrian evacuation through virtual experiments and survey. We conducted a series of multiplayer fire evacuation experiments in Minecraft. The risk information provided to pedestrians before evacuation was controlled at three levels: no risk information, partial risk information, and complete risk information, by giving different risk information cues. The results of experiments indicated that risk information can improve pedestrian evacuation efficiency during fire emergencies, while more complete risk information can further improve pedestrian evacuation efficiency. Additionally, an information transfer phenomenon was observed during fire evacuations, in which pedestrians adjusted their behaviour based on perceived fire, leading others to avoid the fire in advance. The analysis of pedestrian behaviour revealed that pedestrians did not exhibit imitative behaviour in evacuation direction choices during fire emergencies. Pedestrian route choices were significantly influenced by the initial distance of pedestrians relative to the exits. Moreover, complete risk information cues did not significantly influence pedestrians’ route choices compared with partial risk information cues. A post-experimental survey was conducted to assess pedestrians’ route choice preferences under different risk information cue scenarios. The results showed that pedestrians preferred the nearest route.

On the Road Safety: Gender Differences in Risk-Taking Driving Behaviors Among Seniors Aged 65 and Older.

Background/Objectives: Life expectancies have increased in most countries, leading to a higher accident rate among older drivers than their younger counterparts. While numerous studies have analyzed the decline in cognitive abilities and physical limitations as contributing factors, there are other considerations. For instance, younger male drivers tend to take more risks than younger female drivers. However, there is a lack of research and evidence regarding the role of gender in risk-taking among individuals over 65. Given this gap, our current study aims to investigate the relationship between gender and risk propensity in this particular age group. The primary goal was to determine if driving experience affects the gender gap in risk attitude; Methods: We studied risk behavior in both car drivers and pedestrians. Our sample included 200 individuals (101 women), all over 65, with the same weekly driving times. After a brief demographic and anamnestic interview, they completed the Driver Road Risk Perception Scale (DRPS) and the Pedestrian Behavior Appropriateness Perception Scale (PBAS) questionnaires. They also provided information about traffic violations and road crashes; Results: Our research revealed that older male drivers continue to tend to risky behavior, highlighting the need for targeted interventions to improve risk awareness, especially among older men; Conclusions: Our findings suggest that road safety messages should specifically target male drivers as they are less likely to view responsible driving actions, such as observing speed limits, as desirable.

Pedestrian safety behavior modeling method in human-vehicle-intelligence shared road space

In the context of the development of autonomous vehicles sharing road resources with traditional traffic participants in the future, modeling the safe behavior of pedestrians in the shared road space between people, vehicles and intelligence is crucial for the simulation development and reliability and safety testing of autonomous vehicles. To meet this demand, the safe movement behavior of pedestrians is first analyzed, and on this basis, the traditional pedestrian social force model is improved to construct a momentum model for the interactive movement of pedestrians with other pedestrians, traditional vehicles and autonomous vehicles in the shared road space; then, the safety parameters of the model are calibrated using a data set of human-vehicle interactive movement and a genetic algorithm, and a typical shared road space scenario is built to verify the effectiveness of the model. The simulation results show that the model can simulate the real safe movement behavior of pedestrians, and has better simulation effects when used in tasks such as human-vehicle-intelligence shared road space simulation.

New insights into the merging behavior of pedestrians: Quantification of lane competition level

Merging behavior is a complex crowd movement pattern caused by certain architectural features and has triggered serious crowd accidents worldwide. It is not uncommon to find such merging structures on the floor plans of some underground infrastructures, which deserve more detailed studies on special crowd movement patterns to enhance the safety level. Researchers have demonstrated that the unstable emotions and competitive behaviors of pedestrians during underground evacuation need to be taken into account due to the enclosed environment. However, there are no relevant studies focused on the competition characteristics among pedestrians during the merging process in a quantitative way. The comprehensiveness and systematization of the geometric features of typical merging structures, as well as the way to create the perception of competition and conflict among pedestrians during real emergencies also need to be improved. In this paper, we carried out a series of controlled experiments in symmetric and asymmetric merging structures with different channel widths and incentive levels to investigate crowd merging behavior with competition characteristics. The density and delay time within the merging area, as well as the time interval and lane changes before and after merging are analyzed. By introducing and modifying Simpson’s Diversity Index, we proposed a new method for quantifying the competition level among pedestrians during the merging process. It is concluded that the performance of the merging area is sensitive to the channel widths and the merging layouts, and the negative effect of unbalanced walking priority is more significant under high incentive level. The lane competition level during the merging process is correlated with the effects of various geometric features, movement layouts, and incentive levels. The method proposed in this paper brings new insights into the interpretation of merging scenarios and more studies on pedestrian dynamics. We hope that this study could serve as supplementary work for other modeling or field experiment methods to jointly provide more insights into the crowd management strategies in some underground infrastructures.

Study on pedestrian evacuation simulation model considering group behavior

As a crowded place on the university campus, the cafeteria inevitably has many safety hazards, such as fire accidents caused by open flames and large appliances, stampede accidents caused by overcrowding during peak dining hours, etc. Therefore, studying pedestrian evacuation in university campus cafeterias is particularly necessary. Pedestrians on campus mostly travel in groups. Previous studies mainly used continuous models to discuss pedestrian group evacuation behavior. In this study, based on the cellular automaton pedestrian evacuation simulation model, the floor field calculation method was improved. A cellular automaton pedestrian evacuation simulation model considering group behavior was established and applied to the evacuation scenario of students in a university campus cafeteria. The study found that under the different group configurations, the pedestrian ratios, and the pedestrian densities, the pedestrian evacuation efficiency had significant differences. The results showed that when the different group configurations existed in the scenario, the higher the proportion of the pedestrians with three-person front-to-back group configurations, the higher the evacuation efficiency. When only one type of the group configuration existed in the scenario, at low pedestrian density, the evacuation efficiency of the individual pedestrian groups was higher compared to the other six group configurations. While at high pedestrian density, the evacuation efficiency of the three-person front-to-back group configurations was higher. These findings provided important references for pedestrian evacuation in university campus cafeterias and provided insights for the simulation research of group pedestrian evacuation models, contributing to enhancing campus safety management and ensuring the safety of teachers, students, and staff.

Road-crossing behavior and safety of pedestrians facing autonomous vehicles with an acceleration indicator eHMI in VR traffic flow

To support pedestrian road-crossing behavior in the presence of autonomous vehicles (AVs), we propose a novel external Human-Machine Interface (eHMI) that enhances the vehicle’s inherent motion cues, which pedestrians already use in traditional traffic. Based on the Beta Movement, the eHMI design consists of light bands with multiple arrows moving forward or backward to indicate the vehicle’s accelerating or decelerating motion state. We measured pedestrians’ behavior and perceived safety when faced with AVs equipped with this acceleration indicator eHMI in a virtual reality (VR) street scene, where pedestrians had road-crossing tasks and vehicles did not always yield. We found that pedestrians exhibited crossing behavior according to the motion state of the oncoming vehicle. They almost always crossed if the vehicle yielded but considered the gap size to cross when it did not. With the acceleration indicator eHMI, they crossed more frequently if the vehicle yielded, yet less frequently if it did not. Although risky crossings could not be fully prevented, pedestrians crossed faster and maintained larger safety margins when the non-yielding vehicle used this eHMI. Additionally, pedestrians started to cross earlier when the eHMI indicated the vehicle’s decelerating state. Regarding pedestrians’ perceived safety, the eHMI did not increase perceived safety for decelerating vehicles but effectively decreased the perceived safety for accelerating vehicles. These results demonstrate the potential of enhancing vehicles’ inherent motion cues with eHMIs, but also imply that making vehicles’ motion state more apparent might not simply increase pedestrians’ perceived safety. Overall, a trade-off seems to exist that it is pedestrians’ sense of unsafety that leads to their safe road-crossing behavior. Suggestions for future research and VR experiments were also discussed.

Modelling study on pedestrian evacuation dynamics considering exit selection behaviour under flood disaster

Flood spreading in metro stations is a dangerous hazard that frequently causes casualties and property losses. However, pedestrian evacuation under flood spreading scenarios has not been fully investigated. To fill this gap,we propose an extend Floor-Field model incorporating flood spreading and exit selection behaviour of individuals. In the model, the dynamic flood spreading process on metro platforms is expressed by using a simulation software named Mike21. The optimal exit selected by pedestrians in each step is decided on three factors, that is pedestrian density around the exit, pedestrian distance to the exit, and water depth at the exit. Meanwhile, the movement speed of pedestrain also changes with the water depth at each time step. Based on this, the transition probability to neighbor cell including static field, dynamic field, height field, and water flow field is calculated. This results in a flood evacuation model considering the pedestrian's behaviour when choosing an exit. The effects of flooding, pedestrian density, different exit selection behaviours, water flow field, and inlet flow on evacuation were thoroughly analysed. The analysis demonstrates that the likelihood of flooding significantly impacts the evacuation of pedestrians from the subway station; the more flooding is taken into account, the more influential the impact. In addition, the effect of inlet flow on evacuation is also noteworthy; considering exit selection behaviour can significantly increase the effectiveness of evacuation. The study's findings can be used to develop evacuation plans for flooded metro stations.

Improving safe pedestrian behavior through virtual reality: an empirical study

INTRODUCTION. Over the last few years, the number of pedestrian fatalities on urban roads has increased, largely due to infractions associated with their behaviors (e.g., crossing when traffic lights are red). It is argued that these behaviors reflect a lack of risk perception. Road safety programs have tried to raise awareness through various methods, using quite often emotionally powerful experiences (e.g. testimonies of people who have experienced an accident themselves). Recently, Virtual Reality (VR) has been deployed with the aim of increasing the efficacy of these safety programs. Previous studies have demonstrated the potential of VR to improve pedestrian safety, especially when it is accompanied bydebriefing and critical reflection. METHOD. A total of 43 participants (M = 24.5 years old; SD = 5.14; 65.12% female) were involved in an experimental study with a 2x2 factorial design and pre-post measures. They were randomly assigned to one of four groups (Experience a VR accident /Experience VR without an accident; having a debriefing after the VR experience/not having a debriefing after the VR experience). Pre-post measures were of two kinds, (a) self-report measures and (b)VR behavioral measures. Multivariate Analysis of Variance (MANOVA) and general linear mixed models (GLMM) were used to analyze the data. RESULTS AND DISCUSSION. The main results revealed that (a) participants reported a general reduction in the number of rules violations, regardless of condition, and (b) there was a significant reduction in the number of violations committed in VR (i.e., crossing when the traffic light is red) in the condition where participants had previously experienced an accident. These results support the potential of using VR environments to improve pedestrian safety-related behavior. Implications for future research are delineated.

Pedestrian Behavior in Static and Dynamic Virtual Road Crossing Experiments

Virtual studies involving pedestrians have gained relevance due to the advantage of not exposing them to actual risk, and simulation setups have benefitted from rapid technical advancements, becoming increasingly complex and immersive. However, it remains unclear whether complex setups affecting participants’ freedom of movement impact their decision-making. This research evaluated the effects of a more realistic approach to studying pedestrian crossing behavior by comparing a perception-action task requiring participants to walk effectively along a semi-virtual crosswalk with a similar experiment using static crossing conditions. Using a CAVE system, two real-world streets were modeled in two different virtual scenarios, varying vehicle speed patterns and distance from the crosswalk. Visual stimuli were presented to two groups of 30 participants, with auditory stimuli adapted accordingly. The impact of various factors on participants’ crossing decisions was evaluated by examining the percentage of crossings, crossing start time, and time-to-passage. Overall, the experimental approach did not significantly affect participants’ crossing decisions.

Impact analysis of street space quality on pedestrian behavior using mobile probe data

Pedestrian-centered streets are being developed to enhance the attractiveness of cities by creating comfortable and walkable spaces. Recent advancements in information and communication technology have allowed for the analysis of the relationship between street spaces and pedestrian behavior using mobile probe data (MPD). This study examined the characteristics of pedestrian behavior around major railway stations using MPD and assessed the impact of street space quality on pedestrian presence and traffic volume. This study utilized the integration value of the Space Syntax theory to measure the street walkability and the size of retail facilities to determine street attractiveness. The results suggested that street space quality played a conditional role in attracting pedestrians and increasing the traffic volume between stations and commercial areas. This analysis method is effective for identifying the streets where the street space between origins and destinations is underestimated in relation to traffic volume. This can facilitate efforts to convert streets into pedestrian-friendly spaces, thereby enhancing walkability.

Prudent behavior of young pedestrians: What are the determinants?

Every year, more than three hundred thousand pedestrians die on roads worldwide, with road traffic injuries the leading cause of death for young less than 30. Since pedestrians are among the most vulnerable road users, they often behave cautiously, especially in contexts that are aggressive toward them. In contrast, other pedestrians are less cautious and engage in riskier behavior. This study assesses the factors determining prudent young pedestrian behavior in Barranquilla, Colombia, an aggressive environment for active modes. A survey (n = 988) was designed to collect information on young individuals’ socioeconomic characteristics, knowledge of traffic rules, prudent pedestrian behavior, and affinity for walking. The analysis was conducted using a Structural Equation Model. Results suggest that young pedestrians’ prudent behavior is influenced by gender (women behave more prudent than men), attitudes in favor of walking (people more attuned to walking are less cautious), and proper knowledge of traffic norms (those with a better understanding of traffic rules are more prudent when walking). The results highlight the need to study young pedestrians’ behavior and risk perception. Policy implications for providing safer pedestrian environments and reducing risky behaviors are discussed based on the findings.

Rescue guiders layout study based on a two-layer optimization framework

In an emergency evacuation, the free evacuation of pedestrians can make the entire evacuation process slow and dangerous. To limit the free behavior of pedestrians and reduce the interaction between pedestrians, a reasonable layout of the guider can improve the efficiency and safety of evacuation. How to set the number, location, and exit allocation of guiders requires further investigation. In the current study, we transform the evacuation into a multi-objective optimization problem. A two-layer optimization framework is developed. In the upper level, the improved NSGA-II multi-objective algorithm is introduced to generate the favorable guider layout, and a chromosome fragment deletion operator is added to improve the optimization efficiency. In the lower layer, the agent movement simulation model is used to simulate the evacuation dynamic of crowd under the favorable guider layout. The variables of this multi-objective solution model in the upper layer are the number and location of the guiders. The evacuation time and agent movement cost are calculated by the lower layer simulation as the objective values of the solution sample, and guide the iterative search process to obtain more reasonable optimization results. The developed model is verified and then applied to a fictional scenario. The number, initial position and exit allocation of guiders are obtained by optimizing the iterative process. The results show that the near optimal solution can be applied in various visibility conditions, and the evacuation efficiency is much higher than that of unguided evacuation. This optimization framework can provide theoretical and methodological support for emergency evacuation planning.

Multiscale Analysis of Pedestrian Crossing Distance

Problem, research strategy, and findings Crossing distance is considered a factor in both pedestrian safety and behavior. However, it has seldom been quantified within or across entire cities or related to walking outcomes. Combining data encoded in OpenStreetMap and drawn from high-resolution satellite imagery, we measured formal pedestrian crossings throughout a dense European city (Paris [France]), a dense American city (San Francisco [CA]), and a less-dense, more car-centric American city (Irvine [CA]). This granular approach—covering roughly 49,000 total crossings—identified inter- and intraurban spatial patterns in the distribution of pedestrian crossing distance, including clusters of long crossings that likely deter walking and increase its risk. By overlaying recent pedestrian–vehicle collisions on these novel data sets we found that longer crossing distance correlated with increased likelihood of collisions, raising the salience of traffic-calming interventions. Takeaway for practice Quantifying pedestrian crossing distance at the scale of entire municipalities empowers transportation planners to identify pedestrian-hostile crossings (individuals and clusters), add context to collision trends, and geographically target locations for traffic calming. These cases collectively demonstrate how the increasing prioritization of the automobile in city planning quantitatively changes (and degrades) the pedestrian environment, as well as how low-tech investments, such as sidewalk extensions and refuge islands, can mitigate these trends.

Design of a Semi-Autonomous Vehicle Using Reinforcement Machine Learning for the Indian Infrastructure

The rapid growth in the transportation sector demands innovative solutions to address safety, efficiency, and environmental challenges, especially in countries with complex and dynamic road infrastructures like India. This research explores the design of a semi-autonomous vehicle tailored for Indian road conditions using reinforcement learning (RL) techniques. The unique characteristics of Indian infrastructure, including mixed traffic, unpredictable behavior of pedestrians, varying road conditions, and inconsistent adherence to traffic regulations, pose challenges to the implementation of autonomous driving technologies. This paper proposes an RL-based approach to navigate these challenges and discusses the potential design, algorithmic frameworks, practical case studies, and implications.

Analysis of pedestrian second crossing behavior based on physics-informed neural networks

Pedestrian two-stage crossings are common at large, busy signalized intersections with long crosswalks and high traffic volumes. This design aims to address pedestrian operation and safety by allowing navigation in two stages, negotiating each traffic direction separately. Understanding crosswalk behavior, especially during bidirectional interactions, is essential. This paper presents a two-stage pedestrian crossing model based on Physics-Informed Neural Networks (PINNs), incorporating fluid dynamics equations to determine characteristics such as speed, density, acceleration, and Reynolds number during crossings. The study shows that PINNs outperform traditional deep learning methods in calculating and predicting pedestrian fluid properties, achieving a mean squared error as low as 10–8. The model effectively captures dynamic pedestrian flow characteristics and provides insights into pedestrian behavior impacts. The results are significant for designing pedestrian facilities to ensure comfort and optimizing signal timing to enhance mobility and safety. Additionally, these findings can aid autonomous vehicles in better understanding pedestrian intentions in intelligent transportation systems.

Estimating the Capacity of Railway Platforms and Stations

Knowing the capacity and the speed-density relation for different facility parts is a key component for a sustainable station design. But as the behaviour of pedestrians on railway platforms is complex, detailed data from railway stations is needed, which only became available recently. By using real-life tracking data from different railway stations in Switzerland, a method to estimate the capacity for different facility elements was derived and applied to the data aiming at verifying or improving the existing design values. As expressed in the fundamental diagram, the speed-density relation was useful in addressing these issues. The speed-density-flow relation was plotted at different levels ranging from a whole platform section to areas covering only a few square meters. Waiting pedestrians were treated separately to reflect their specific behaviour. Afterwards, the Kladek-curve proposed by Weidmann was fitted to the data using different parameter values. Although the data is biased towards low densities, the capacity of each area can be estimated using the fitted curve. The results show that the flow-density curves show a good fit to the mean of each density bin. Nevertheless, a large scatter of the individual data points exists. The derived maximum flow is considerably different depending on the measurement location and the area size and is generally lower than average values from literature. It is expected that the complex behaviour of pedestrians in railway stations and platforms has a significant influence on these differences, which therefore needs to be considered for station design.